Litcius/Paper detail

Deep reinforcement learning for time-critical wilderness search and rescue using drones

Jan‐Hendrik Ewers, David Anderson, Douglas Thomson

2025Frontiers in Robotics and AI10 citationsDOIOpen Access PDF

Abstract

Traditional search and rescue methods in wilderness areas can be time-consuming and have limited coverage. Drones offer a faster and more flexible solution, but optimizing their search paths is crucial for effective operations. This paper proposes a novel algorithm using deep reinforcement learning to create efficient search paths for drones in wilderness environments. Our approach leverages a priori data about the search area and the missing person in the form of a probability distribution map. This allows the policy to learn optimal flight paths that maximize the probability of finding the missing person quickly. Experimental results show that our method achieves a significant improvement in search times compared to traditional coverage planning and search planning algorithms by over <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="m1"><mml:mrow><mml:mn>160</mml:mn><mml:mi>%</mml:mi></mml:mrow></mml:math> , a difference that can mean life or death in real-world search operations Additionally, unlike previous work, our approach incorporates a continuous action space enabled by cubature, allowing for more nuanced flight patterns.

Topics & Concepts

Reinforcement learningComputer scienceDroneWildernessA priori and a posterioriWilderness areaArtificial intelligenceSearch and rescueSearch algorithmMachine learningAlgorithmRobotEpistemologyBiologyPhilosophyGeneticsEcologyRobotic Path Planning AlgorithmsReinforcement Learning in RoboticsRobotics and Sensor-Based Localization
Deep reinforcement learning for time-critical wilderness search and rescue using drones | Litcius